论文标题
动态区域感知卷积
Dynamic Region-Aware Convolution
论文作者
论文摘要
我们提出了一个称为动态区域感知卷积（DRCONV）的新卷积，该卷积可以自动将多个过滤器分配给相应的空间区域，在该空间区域具有相似的表示。通过这种方式，DRCONV在建模语义变化时优于标准卷积。标准卷积层可以增加提取更多视觉元素的申报人数，但会导致高计算成本。更优雅地，我们的DRCONV通过可学习的讲师将增加的频道过滤器转移到空间维度，这不仅提高了卷积的表示能力，而且还保持了计算成本和翻译不变性作为标准卷积剂量。 DRCONV是一种处理复杂和可变空间信息分布的有效而优雅的方法。它可以在任何现有网络中替代标准卷积的插件属性，尤其是在有效网络中的电力卷积层。我们对DRCONV进行了广泛的模型（Mobilenet系列，ShufflenetV2等）和任务（分类，面部识别，检测和分割）的评估。在ImageNet分类中，基于DRCONV的ShuffleNetv2-0.5X在46m多重添加水平下达到67.1％的最新性能，相对改善为6.3％。
We propose a new convolution called Dynamic Region-Aware Convolution (DRConv), which can automatically assign multiple filters to corresponding spatial regions where features have similar representation. In this way, DRConv outperforms standard convolution in modeling semantic variations. Standard convolutional layer can increase the number of filers to extract more visual elements but results in high computational cost. More gracefully, our DRConv transfers the increasing channel-wise filters to spatial dimension with learnable instructor, which not only improve representation ability of convolution, but also maintains computational cost and the translation-invariance as standard convolution dose. DRConv is an effective and elegant method for handling complex and variable spatial information distribution. It can substitute standard convolution in any existing networks for its plug-and-play property, especially to power convolution layers in efficient networks. We evaluate DRConv on a wide range of models (MobileNet series, ShuffleNetV2, etc.) and tasks (Classification, Face Recognition, Detection and Segmentation). On ImageNet classification, DRConv-based ShuffleNetV2-0.5x achieves state-of-the-art performance of 67.1% at 46M multiply-adds level with 6.3% relative improvement.
